|
|
Course Criteria
Add courses to your favorites to save, share, and find your best transfer school.
-
3.00 Credits
Covers the use of algorithms in machine learning, including decision trees, Bayesian learning, genetic algorithms, and reinforcement learning. This course also covers basic theoretical concepts, such as Occam's razor, inductive bias, VC dimension, and PAC learnability. Students are expected to have familiarity with programming, linear algebra, and statistics before enrolling in this course.
-
3.00 Credits
Covers the principles of recently developed algorithms in deep learning, such as convolutional neural networks, recursive neural networks, generative adversarial nets and deep reinforcement learning, self-attention, deep neural networks, auto encoders, and VAE. Students are expected to have familiarity with programming, linear algebra, and statistics before enrolling in this course.
-
3.00 Credits
Covers algorithms such as dynamic programming for biological problems, including sequence alignment and phylogeny tree constructions; statistical and mathematical modeling of high throughput data, such as differentially expressed genes from microarray data and HMM for gene prediction; graph and network theory for biological networks.
-
3.00 Credits
Basic theory and practical algorithms in information retrieval, including indexing, vector space models, evaluation methods, probabilistic and language models of information retrieval, and web search.
-
3.00 Credits
Networks and network models arise in many places, from physical complex systems, communications, and electrical circuits, to social science and bioinformatics. This course teaches the common theory of abstract and real-world networks, including models, metrics, visualization, representation, comparison and organization. Students are expected to have basic programming skills and introductory knowledge of linear algebra, probability and statistics before enrolling in this course.
-
3.00 Credits
Basic techniques and fundamental problems of numerical computation with an emphasis on big data. Focus is placed on practical data analysis questions that arise in areas such as engineering, health care, natural science and economics. Methods are discussed in the context of machine learning, data mining and computational problems on graphs. Students are expected to have basic knowledge of linear algebra, calculus, programming and data structures before enrolling in this course.
-
3.00 Credits
Structure of software systems supporting communications among computing devices having diverse processing and communication capabilities; characterization of data communications software in terms of unified network architectures consisting of several functional layers; evaluation of several network architectures.
-
3.00 Credits
Network architecture and communication protocols underlying the global interoperability of the Internet. Topics include addressing and routing, interconnection of autonomous networks, naming and name resolution, connection management, flow and congestion control and network management. Students are expected to be familiar with computer networking fundamentals before enrolling in this course.
-
3.00 Credits
Discusses hardware fundamentals, technology applications, operating systems, programming platforms, software design and implementation, energy conservation techniques, self-stabilization paradigm, routing algorithms, clustering algorithms, time synchronization algorithms and sensor-actuator integration.
-
3.00 Credits
Security issues in emerging networking technologies, including Software-Defined Networking (SDN) and Network Function Virtualization (NFV). Students are expected to have completed coursework in computer networking before enrolling in this course.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|